Majid Janidarmian

Onyx: A new heuristic bandwidth-constrained mapping of cores onto tile-based Network on Chip

Due to the ever-increasing complexity of System on Chip (SoC) design, and non-efficiency of electric bus to exchange data between IP cores in Giga scale, the Network on Chip (NoC) is presented with more flexible, scalable and reliable infra-structure. As mapping of IP cores on a given platform is one of three aspects of NoC design, with the focus on tile-based NoC architecture, we have introduced a heuristic method for mapping cores on mesh platform. Onyx1 algorithm is a method with less complexity, and it minimizes hop count between IP cores, leading to improving energy consumption and other performance parameters. We have used this method with two real applications, i.e. VOPD2, and MPEG-4 and compared it with some existing algorithms. The results show that our developed method is more efficient.

A Medical Cloud-Based Platform for Respiration Rate Measurement and Hierarchical Classification of Breath Disorders

The measurement of human respiratory signals is crucial in cyberbiological systems. A disordered breathing pattern can be the first symptom of different physiological, mechanical, or psychological dysfunctions. Therefore, a real-time monitoring of the respiration patterns, as well as respiration rate is a critical need in medical applications. There are several methods for respiration rate measurement. However, despite their accuracy, these methods are expensive and could not be integrated in a body sensor network. In this work, we present a real-time cloud-based platform for both monitoring the respiration rate and breath pattern classification, remotely. The proposed system is designed particularly for patients with breathing problems (e.g., respiratory complications after surgery) or sleep disorders. Our system includes calibrated accelerometer sensor, Bluetooth Low Energy (BLE) and cloud-computing model. We also suggest a procedure to improve the accuracy of respiration rate for patients at rest positions. The overall error in the respiration rate calculation is obtained 0.53% considering SPR-BTA spirometer as the reference. Five types of respiration disorders, Bradapnea, Tachypnea, Cheyn-stokes, Kaussmal, and Biots breathing are classified based on hierarchical Support Vector Machine (SVM) with seven different features. We have evaluated the performance of the proposed classification while it is individualized to every subject (case 1) as well as considering all subjects (case 2). Since the selection of kernel function is a key factor to decide SVMs performance, in this paper three different kernel functions are evaluated. The experiments are conducted with 11 subjects and the average accuracy of 94.52% for case 1 and the accuracy of 81.29% for case 2 are achieved based on Radial Basis Function (RBF). Finally, a performance evaluation has been done for normal and impaired subjects considering sensitivity, specificity and G-mean parameters of different kernel functions.

Chain-Mapping for mesh based Network-on-Chip architecture

Mapping of IP cores on a given platform is one of the three aspects of Network-on-Chip design. Mapping priority of IP cores is mostly based on a single communication in previously proposed algorithms. In this paper we present Chain-Mapping (CHMAP), as an algorithm for mapping cores onto a mesh-based Network-on-Chip architecture. The main aim of the algorithm is to produce chains of connected cores in order to introduce a new method to prioritize IP core which helps us to have more efficient mapping. Proposed algorithm and previous researches were compared on two real applications, i.e. Video object plan decoder (VOPD) and MPEG-4 and results were reported.

A Comprehensive Analysis on Wearable Acceleration Sensors in Human Activity Recognition

Sensor-based motion recognition integrates the emerging area of wearable sensors with novel machine learning techniques to make sense of low-level sensor data and provide rich contextual information in a real-life application. Although Human Activity Recognition (HAR) problem has been drawing the attention of researchers, it is still a subject of much debate due to the diverse nature of human activities and their tracking methods. Finding the best predictive model in this problem while considering different sources of heterogeneities can be very difficult to analyze theoretically, which stresses the need of an experimental study. Therefore, in this paper, we first create the most complete dataset, focusing on accelerometer sensors, with various sources of heterogeneities. We then conduct an extensive analysis on feature representations and classification techniques (the most comprehensive comparison yet with 293 classifiers) for activity recognition. Principal component analysis is applied to reduce the feature vector dimension while keeping essential information. The average classification accuracy of eight sensor positions is reported to be 96.44% ± 1.62% with 10-fold evaluation, whereas accuracy of 79.92% ± 9.68% is reached in the subject-independent evaluation. This study presents significant evidence that we can build predictive models for HAR problem under more realistic conditions, and still achieve highly accurate results.

MSE minimization and fault-tolerant data fusion for multi-sensor systems

Multi-sensor data fusion is an efficient method to provide both accurate and fault-tolerant sensor readouts. Furthermore, detection of faults in a reasonably short amount of time is crucial for applications dealing with high risks. In order to deliver high accuracies for the sensor measurements, it is required to perform a calibration for each sensor. This paper focuses on designing a fault-tolerant calibrated multisensor system. First, the least squares method is applied to calibrate each sensor using a linear curve fitting function. Next, an analytical technique is proposed to carry out a fault-tolerant multi-sensor data fusion, while minimizing the Mean-Square-Error (MSE) for the final sensor readout. While our data fusion approach is applicable to different multi-sensor systems, the experimental results are shown for 16 temperature sensors, where an environmental thermal chamber was used as the reference model to calibrate the sensors and perform the measurements.

Respiration Disorders Classification With Informative Features for m-Health Applications

Respiratory disorder is a highly prevalent condition associated with many adverse health problems. As the current means of diagnosis are obtrusive and ill-suited for real-time m-health applications, we explore a convenient and low-cost automatic approach that uses wearable microelectromechanical system sensor technology. The proposed system introduces the use of motion sensors to detect the changes in the anterior-posterior diameter of the chest wall during breathing function as well as extracting the informative respiratory features to be used for breathing disorders classification. Extensive evaluations are provided on six well-known classifiers with novel feature extraction techniques to distinguish among eight different pathological breathing patterns. The effects of the number of sensors, sensor placement, as well as feature selection on the classification performance are discussed. The experimental results conducted with ten subjects show the best accuracy rates of 97.50% by support vector machine and 97.37% with decision tree bagging (DTB) with all features and after feature selection, correspondingly. Furthermore, a binary classification is proposed for distinguishing between healthy people and patients with breath problems. The different assessments of classification parameters are provided by measuring the accuracy, sensitivity, specificity, F1-score and Mathew correlation coefficient. The accuracy rates above 98% suggest superior performance of DTB in binary recognition supported by the suggested new features.

Sorena: New on Chip Network Topology Featuring Efficient Mapping and Simple Deadlock Free Routing Algorithm

This paper presents a new topology for network-on-chip (NoC) called “Sorena”. The proposed topology is made by merging of 4-node basic models and then connecting edge nodes. Using a change in coordinate system of nodes, a simple, fast and deadlock-free routing algorithm has been suggested. Compared to 2D Mesh which is the most common topology in on chip networks with its high expandability and simple routing algorithms, Sorena shows better average latency and power consumption. Finally, Onyx mapping, one of the best algorithms at mapping of cores onto Mesh based NoC architectures, has been implemented onto Sorena. Results demonstrate that Sorena also has much more suitable structure to implement mapping algorithms comparing to Mesh topology.

Special Issue on a Fault Tolerant Network on Chip Architecture

In this paper a fast and efficient spare switch selection algorithm is presented in a reliable NoC architecture based on specific application mapped onto mesh topology called FERNA. Based on ring concept used in FERNA, this algorithm achieves best results equivalent to exhaustive algorithm with much less run time improving two parameters. Inputs of FERNA algorithm for response time of the system and extra communication cost minimization are derived from simulation of high transaction level using SystemC TLM and mathematical formulation, respectively. The results demonstrate that improvement of above mentioned parameters lead to advance whole system reliability that is analytically calculated. Mapping algorithm has been also investigated as an effective issue on extra bandwidth requirement and system reliability.

Development of a Remote Monitoring System for Respiratory Analysis

In order to prevent the lack of appropriate respiratory ventilation which causes brain damage and critical problems, it is required to continuously monitor the breathing signal of a patient. There are different conventional methods for capturing respiration signal, such as polysomnography and spirometer. In spite of their accuracy, these methods are expensive and could not be integrated in a body sensor network. In this work, we present a real-time cloud-based respiration monitoring platform which allows the patient to continue treatment and diagnosis from different places such as home. These remote services are designed for patients who suffer from breathing problems or sleep disorders. Our system includes calibrated accelerometer sensor, Bluetooth Low Energy (BLE) and cloud database. Based on the high correlation between spirometer and accelerometer signals, the Detrended Fluctuation Analysis (DFA) has been applied on respiration signals. The obtained results show that DFA can be used as an efficient feature while classifying the healthy people from patients suffering from breath abnormalities.

Multi-sensor blind recalibration in mHealth applications

This paper considers the problem of self-calibration of multi-sensor systems for health care cyber-biological systems, such as closed-loop glucose control. The recalibration method is performed periodically in the cloud resulted in significant advantages over traditional methods, including increased on-line accessibility and fast automated recovery from failures. Since the size of dataset has direct impact on the recalibration quality, we use cloud database which let us have a more complete recalibration dataset compared to limited on-board logging at different times and situations. Three methods are presented and evaluated in terms of accuracy and time. The proposed Minimum Mean Square Error (MMSE) recalibration method delivers the superior precision compared to other two techniques which are based on average and correlation. While all these approaches are generic and applicable to different medical multi-sensor systems, the experimental results are evaluated on temperature sensors due to their simple and reliable setup.